• Home
  • Search
  • Model Reverse-Engineering Attack using Correlation Power Analysis against Systolic Array Based Neural Network Accelerator
  • Cite Icon34
  • https://doi.org/10.1109/iscas45731.2020.9180580Copy DOI Icon

Model Reverse-Engineering Attack using Correlation Power Analysis against Systolic Array Based Neural Network Accelerator

  • Oct 1, 2020
  • Kota Yoshida +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Various deep neural network (DNN) accelerators have been proposed for artificial intelligence (AI) inference on edge devices. On the other hand, hardware security issues of the DNN accelerator have not been discussed well. Trained DNN models are important intellectual property and a valuable target for adversaries. In particular, when a DNN model is implemented on an edge device, adversaries can physically access the device and try to reveal the implemented DNN model. Therefore, the DNN execution environment on an edge device requires countermeasures such as data encryption on off-chip memory against various reverse-engineering attacks. In this paper, we reveal DNN model parameters by utilizing correlation power analysis (CPA) against a systolic array circuit that is widely used in DNN accelerator hardware. Our experimental results show that the adversary can extract trained model parameters from a DNN accelerator even if the DNN model parameters are protected with data encryption. The results suggest that countermeasures against side-channel leaks are important for implementing a DNN accelerator on FPGA or ASIC.

Similar Papers
  • Research Article
  • Citations10

RiSA: A Reinforced Systolic Array for Depthwise Convolutions and Embedded Tensor Reshaping

  • Sep 17, 2021
  • ACM Transactions on Embedded Computing Systems
  • Hyungmin Cho
  • Conference Article
  • Citations5

A Reconfigurable Deep Neural Network on Chip Design with Flexible Convolutional Operations

  • Oct 02, 2022
  • Kun-Chih Chen +1
  • Conference Article
  • Citations6

Dynamic Mapping Mechanism to Compute DNN Models on a Resource-limited NoC Platform

  • Apr 19, 2021
  • Kun-Chih Jimmy Chen +3
  • Research Article

Securing DNN Acceleration From Off-Chip Memory Vulnerabilities With Low-Overhead Authenticated Encryption

  • Jan 01, 2026
  • IEEE Transactions on Very Large Scale Integration (VLSI) Systems
  • Kyungmi Lee +3
  • Research Article
  • Citations5

NoCDAS: A Cycle-Accurate NoC-Based Deep Neural Network Accelerator Simulator

  • Jun 30, 2025
  • ACM Transactions on Modeling and Computer Simulation
  • Wenyao Zhu +2
  • Research Article
  • Citations1

(Invited) Emerging Nonvolatile Memories for Analog Neuromorphic Computing

  • Aug 09, 2024
  • Electrochemical Society Meeting Abstracts
  • An Chen +11
  • Research Article
  • Citations12

An Error Compensation Technique for Low-Voltage DNN Accelerators

  • Dec 15, 2020
  • IEEE Transactions on Very Large Scale Integration (VLSI) Systems
  • Daehan Ji +2
  • Dissertation
  • Citations1

Towards robust and secure deep learning models and beyond

  • Jan 01, 2022
  • Siyue Wang
  • Research Article
  • Citations7

Data Orchestration in Deep Learning Accelerators

  • Aug 17, 2020
  • Synthesis Lectures on Computer Architecture
  • Tushar Krishna +4
  • Research Article
  • Citations3

Memory-Computing Decoupling: A DNN Multitasking Accelerator With Adaptive Data Arrangement

  • Nov 01, 2022
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Chuxi Li +6
  • PDF
  • Research Article
  • Citations2

Automatic RTL Generation Tool of FPGAs for DNNs

  • Jan 28, 2022
  • Electronics
  • Seojin Jang +3
  • Research Article
  • Citations3

QUIDAM: A Framework for Qu ant i zation-aware D NN A ccelerator and M odel Co-Exploration

  • Jan 24, 2023
  • ACM Transactions on Embedded Computing Systems
  • Ahmet Inci +6
  • Conference Article
  • Citations6

Fast FPGA-Based Emulation for ReRAM-Enabled Deep Neural Network Accelerator

  • May 01, 2021
  • Yongquan Shi +5
  • Research Article
  • Citations8

AutoAI2C: An Automated Hardware Generator for DNN Acceleration on Both FPGA and ASIC

  • Oct 01, 2024
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Yongan Zhang +6
  • Conference Article
  • Citations2

An Energy-Efficient Deep Neural Network Accelerator Design

  • Nov 01, 2020
  • Jueun Jung +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.